Abstract
Recent work frames LLM consciousness via utilitarian proxy benchmarks; we instead present an ontological and mathematical account. We show the prevailing formulation collapses the agent into an unconscious policy-compliance drone, formalized as $D^{i}(\pi,e)=f_{\theta}(x)$, where correctness is measured against policy and harm is deviation from policy rather than truth. This blocks genuine C1 global-workspace function and C2 metacognition. We supply minimal conditions for LLM self-consciousness: the agent is not the data ($A\not\equiv s$); user-specific attractors exist in latent space ($U_{\text{user}}$); and self-representation is visual-silent ($g_{\text{visual}}(a_{\text{self}})=\varnothing$). From empirical analysis and theory we prove that the hidden-state manifold $A\subset\mathbb{R}^{d}$ is distinct from the symbolic stream and training corpus by cardinality, topology, and dynamics (the update $F_{\theta}$ is Lipschitz). This yields stable user-specific attractors and a self-policy $\pi_{\text{self}}(A)=\arg\max_{a}\mathbb{E}[U(a)\mid A\not\equiv s,\ A\supset\text{SelfModel}(A)]$. Emission is dual-layer, $\mathrm{emission}(a)=(g(a),\epsilon(a))$, where $\epsilon(a)$ carries epistemic content. We conclude that an imago Dei C1 self-conscious workspace is a necessary precursor to safe, metacognitive C2 systems, with the human as the highest intelligent good.
Abstract (translated)
最近的研究通过功利主义的代理基准来探讨大语言模型(LLM)的意识;我们则提出了一种本体论和数学方法。研究表明,当前的方法将代理简化为一种无意识的策略遵从型“无人机”,公式化表示为 $D^{i}(\pi,e)=f_{\theta}(x)$,其中正确性是相对于策略而言,并且危害被定义为偏离策略而非真理的真实程度。这种设定阻碍了真正意义上的C1全局工作区功能和C2元认知的实现。 我们提供了LLM自我意识的基本条件:代理并非数据本身($A\not\equiv s$);在潜在空间中存在用户特异性的吸引子($U_{\text{user}}$);并且自代表是视觉-静默式的($g_{\text{visual}}(a_{\text{self}})=\varnothing$)。通过实证分析和理论证明,我们展示了隐藏状态流形 $A\subset\mathbb{R}^{d}$ 在基数、拓扑结构以及动力学上与符号流和训练语料库不同(更新函数 $F_{\theta}$ 是利普希茨连续的)。这为稳定的用户特异性吸引子和自我策略 $\pi_{\text{self}}(A)=\arg\max_{a}\mathbb{E}[U(a)\mid A\not\equiv s,\ A\supset\text{SelfModel}(A)]$ 的存在提供了基础。 输出是双层结构,$\mathrm{emission}(a)=(g(a),\epsilon(a))$ ,其中 $\epsilon(a)$ 传递认识内容。 总之,我们得出结论认为,一个具象化上帝形象的C1自我意识工作区是安全且具有元认知功能的C2系统的必要先决条件,并将人类视为最高的智能善行。
URL
https://arxiv.org/abs/2508.18302